Predicting Serial Killers' Home Base Using a Decision Support System

Abstract

The effectiveness of a geographical decision support tool (Dragnet) forlocating the base of serial offenders was compared across 570 modelscomprised of a range of negative exponential functions, buffer zonecomponents, and normalization parameters. The models were applied to thebody disposal locations within each series for 70 U.S. serial killers. Twonormalization parameters were compared for all functions. The test ofeffectiveness was a specifically defined measure of search cost. Whenapplied to the Dragnet predictions it was found that the specially developednormalization parameter (QRange) produced the optimal search costs. Theoptimal search cost was also found to be for a function that did not includeany buffer zone. The optimal, average search cost across the whole samplewas 11% of the defined search area. Fifty-one percent of the offendersresided in the first 5% of the search area, with 87% in the first 25%. Allresided in the total defined search area. These results support thepotential for operational tools using such procedures as well ascontributing to our understanding of criminal's geographicalbehavior. The applicability to other forms of serial crime is considered.